INDEX

Explanations

phrases indicative of actions or states of being, particularly those involving subjects and objects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ौर

-0.57

あります

-0.54

ある

-0.54

かもしれない

-0.51

EndContext

-0.49

あった

-0.48

Fod

-0.48

多い

-0.48

sian

-0.48

side

-0.47

POSITIVE LOGITS

 فريبيس

1.04

Rüyada

0.80

nodoc

0.79

)]=

0.77

XmlAccessorType

0.75

السكان

0.74

 invokingState

0.73

 GoogleFonts

0.73

CppMethod

0.72

AsUp

0.70

Activations Density 0.039%

phrases indicative of actions or states of being, particularly those involving subjects and objects

No Comments

No Known Activations